Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'read-only, free, no parameters' largely restates structured data. The description still earns credit for disclosing the return shape (data.status, data.version) and for bounding expectations with 'does not measure data freshness', which annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: purpose first, then routing guidance, then return shape and limitation. No filler, and the most decision-relevant information leads.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description correctly carries the return contract itself (data.status = "ok", data.version). Combined with the routing guidance and the stated limitation, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters and the description confirms that ('no parameters'), matching the empty schema exactly. Baseline for a 0-param tool applies; there is nothing further to disambiguate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: check reachability of the Agents Trust API and read its deployed version. It also names what it is not (a data-freshness check), so an agent can separate it from recommend/inspect without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to call it — diagnose connection problems before retrying recommend or inspect — and explicitly excludes a neighboring concern (data freshness). Both the trigger and the non-use case are stated, not inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already disclose the key traits (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds substantial context about side effects: payment, unindexed URLs returning ENDPOINT_NOT_INDEXED without charge, wallet env-var prerequisites, per-process paid-call limits, and no retries on paid calls. Return shape is only partially covered (keys named, no field semantics), which leaves moderate gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose and the recommend alternative in the first two sentences, then layers cost, prerequisites, and return shape. Dense and mostly waste-free, though the payment/limit clause runs long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers intent, alternatives, cost model, error semantics, auth requirements, and a return-value sketch for a 2-parameter paid tool with no output schema. Nothing material for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both parameters including the view enum; the description adds only the URL-domain detail (exact x402 endpoint, unindexed URLs error out before payment). This is useful but does not explain the view modes beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource (read stored evidence for one exact x402 endpoint URL) and enumerates what the evidence contains: price, networks, liveness, delivery history, risk flags. It also explicitly carves out what it does not do (never calls or pays the endpoint) and contrasts with the recommend sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit decision rule: use inspect before paying an endpoint you already know (e.g. from recommend), and use recommend instead to discover candidates. Cost and precondition rules (demo free, 1% of quoted price, 0.001 USDC minimum) further clarify when a call is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnly/idempotent/non-destructive, but the description adds information they cannot carry: the call is free, it never re-triggers the paid request, an unknown id returns a not-found error, and a pending state is not proof that no charge occurred. It also enumerates the four possible settlement states, so the agent knows the full outcome space before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose, cost, when-to-use, parameter source, return shape, error case and the safety caveat each appear once, in that order. Nothing is repeated and the most decision-relevant facts come first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description names the returned fields (data.state with all four values, data.transaction with its null case) and the error behavior. For a one-parameter polling tool, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter already documents its provenance and UUIDv7 format. The description repeats that the id comes from the preceding paid call, which reinforces usage but adds no new semantics about the value itself, so the baseline holds.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: check whether a paid answer has settled on-chain. It scopes the tool to post-payment polling, which clearly separates it from the siblings recommend, inspect and health that the agent would otherwise confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('use it after a paid call, with the payment_attempt_id that call returned') and an explicit caution about what to do when the answer is pending ('check the wallet before paying again'). It also rules out a wrong inference ('pending or unavailable does not prove no money moved').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description goes far beyond by disclosing the payment prerequisites (AGENTS_TRUST_ENABLE_PAYMENTS, wallet key, Base USDC), the one-paid-call-per-process limit and AGENTS_TRUST_MAX_CALL_USDC cap, the error-and-no-send path, the no-retry rule for paid calls, and which outcomes are free. Nothing here contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and the sibling routing before the payment mechanics, and every clause carries operational information. It is dense and slightly run-on in the payment sentence, but no sentence is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, open-world tool with no output schema, the description still names the return keys ({data, payment_attempt_id, request_id}), explains when payment_attempt_id is set, and warns that results may be fewer or empty when evidence is insufficient. An agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all six parameters including the live const, chain CAIP-2 pattern and limit bounds are already documented in the schema. The description adds cost context around max_price_usd being separate from the recommendation fee, but does not describe need, view, chain or limit beyond what the schema says, so the baseline of 3 holds.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find which paid x402 API to call') plus the input form (plain words) and output shape (ranked picks with evidence). It explicitly distinguishes itself from both siblings by naming when inspect and receipt apply instead.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use rule ('when you do not yet know which API to call') and names the alternatives with the exact condition that selects them: inspect for a known endpoint URL, receipt to confirm settlement after paying. It also flags which needs are free demos versus paid.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.